Journal Title : International Journal of Modern Trends in Engineering and Science

Author’s Name : S.Tharani, P.S.Periasamy

Volume 01 Issue o5  Year 2014  

ISSN no:  2348-3121

Page no: 158-161

Abstract—Intensive research has been done on optical character recognition (OCR) and a more number of articles have been published on this topic during the last few decades. Many commercial OCR systems are available in the market. But most of the systems work for Roman, Chinese, Japanese and Arabic characters. There is no sufficient number of works on Indian language especially Tamil language. Recognition rate of handwritten character is still limited due to presence of large variation of shape, size, scale and format in hand written characters. A complicated hand written character recognition system demands a better feature extraction technique that would take care of such variation of hand writing. This paper presents the application of wavelet processing in the domain of handwritten character recognition for Tamil and English characters. To attain high recognition rate, robust feature extractors and powerful classifiers that are invariant to degree of variability of human writing are needed. The proposed scheme consists of two stages: a feature extraction stage, which is based on Haar wavelet transform and a classification stage that uses neural network.

Keywords—Character recognition, Haar wavelet transform, Neural Network


[1] Jomy John, Pramod K.V & Kannan Balakrishnan, (2012) ‘Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and support vector Machine Classifier’ International Conference on Communication Technology and System Design (2011).
[2] Bharath .A, Sriganesh Madhvanath, Senior member (2012) ‘HMM-Based Lexicon- Driven and Lexicon-Free Word Recognition for Online Handwritten Indic Scripts’ IEEE Transactions on Pattern Analysis and Machine Intelligence, VOL. 34, NO. 4.
[3] AnkitSharma, Dipti.R & Chaudhary,(2012) ‘Character Recognition Using Neural Network’ International Journal of Engineering Trends and Technology (IJETT) – VOL.4Issue4.
[4] Rajakumar.S, Dr.Subbiah Bharathi V. (2012) ‘7th Century Ancient Tamil character recognition from Temple Wall Inscriptions, Proceedings of the World Congress on Engineering 2007 VOL. I WCE (2007), July 2 – 4, (2007), London, U.K.
[5] Suresh.R.M , Arumugam.S, (2007) ‘ Fuzzy technique based recognition of handwritten characters’ www.sciencedirect.com,Image and Vision Computing 25 (2007) 230–239.
[6] Radomir.S, Stankovi.C, Bogdan & Falkowski.J (2003) ‘The Haar wavelet transform: its status and achievements’ Computers and Electrical Engineering 29 (2003) 25–44
[7] Mallat.S.G (1989) ‘A theory for multiresolution signal decomposition:The wavelet representation’. IEEE Trans. On PatternAnalysis and Machine Intelligence, 11(7):674–693.

Full Pdf Paper-Click Here